A Draughts Learning System Based on Neural Networks and Temporal Differences: The Impact of an Efficient Tree-Search Algorithm
- Gutierrez Soares Caexeta, Rita Maria Silva Julia
- Computer ScienceBrazilian Symposium on Artificial Intelligence
- 26 October 2008
New and very successful results obtained by substituting an efficient tree-search module based on alpha-beta pruning, transposition table and iterative deepening for the minimax algorithm in NeuroDraughts are presented.
A Deep Reinforcement Learn-Based FIFA Agent with Naive State Representations and Portable Connection Interfaces
- Matheus Prado Prandini Faria, Rita Maria Silva Julia, Lidia Bononi Paiva Tomaz
- Computer ScienceThe Florida AI Research Society
- 2019
A multiagent player system composed by expert agents in specific game stages operating in high performance environment
- Lidia Bononi Paiva Tomaz, Rita Maria Silva Julia, V. Duarte
- Computer ScienceApplied intelligence (Boston)
- 2017
The results show that D-MA-Draughts improves upon its predecessors by significantly reducing training time and the endgame loops, thus beating them in several tournaments.
LS-Draughts - A Draughts Learning System based on genetic algorithms, neural network and temporal differences
- H. C. Neto, Rita Maria Silva Julia
- Computer ScienceIEEE Congress on Evolutionary Computation
- 1 September 2007
A tournament was promoted between the best player obtained by the LS-Draughts and the best available player of the NeuroDRAughts, which confirms that the GAs can be an important tool for improving the general performance of automatic players.
ACE-RL-Checkers: decision-making adaptability through integration of automatic case elicitation, reinforcement learning, and sequential pattern mining
- H. C. Neto, Rita Maria Silva Julia
- Computer ScienceKnowledge and Information Systems
- 26 February 2018
This study proposes an automatic Checkers player equipped with a dynamic decision-making module, which adapts to the profile of the opponent over the course of the game, and proposes a new module based on sequential pattern mining for generating a base of experience rules extracted from human expert's game records.
LS-VisionDraughts: improving the performance of an agent for checkers by integrating computational intelligence, reinforcement learning and a powerful search method
- H. C. Neto, Rita Maria Silva Julia, Gutierrez Soares Caexeta, Ayres Roberto Araújo Barcelos
- Computer ScienceApplied intelligence (Boston)
- 1 September 2014
LS-VisionDraughts is an efficient unsupervised evolutionary learning system for Checkers whose contribution is to automate the process of selecting an appropriate representation for the board states – by means of Evolutionary Computation – keeping a deep look-ahead at the moment of choosing an adequate move.
Improving the accomplishment of a neural network based agent for draughts that operates in a distributed learning environment
- Lidia Bononi Paiva Tomaz, Rita Maria Silva Julia, Ayres Roberto Araújo Barcelos
- Computer ScienceIEEE International Conference on Information…
- 24 October 2013
This article presents an extension to the system D-VisionDraughts: a draughts player agent based on a MultiLayer Perceptron Neural Network which operates in a distributed environment, and in a manner…
Evaluating the Performance of the Deep Active Imitation Learning Algorithm in the Dynamic Environment of FIFA Player Agents
- Matheus Prado Prandini Faria, Rita Maria Silva Julia, Lidia Bononi Paiva Tomaz
- Computer ScienceInternational Conference on Machine Learning and…
- 1 December 2019
This work investigates the efficacy of DAI to cope with a dynamic FIFA scenario named confrontation mode and indicates that such learning strategy can be used to solve complex problems.
MP-Draughts: Unsupervised Learning Multi-agent System Based on MLP and Adaptive Neural Networks
- V. Duarte, Rita Maria Silva Julia, M. Albertini, H. C. Neto
- Computer ScienceIEEE International Conference on Tools with…
- 9 November 2015
The accomplishment of the best architecture of MP-Draughts found in the investigations performed in this paper was evaluated in terms of the following parameters: coherence and appropriateness of the clustering process, and performance in tournaments against other unsupervised learning-based agents for Checkers.
APHID-Draughts: Comparing the Synchronous and Asynchronous Parallelism Approaches for the Alpha-Beta Algorithm Applied to Checkers
- Lidia Bononi Paiva Tomaz, Rita Maria Silva Julia, Matheus Prado Prandini Faria
- Computer ScienceIEEE International Conference on Tools with…
- 1 November 2017
Comparisons between unsupervised player agents operating according to one of the following alpha-beta parallelism approaches: asynchronous or synchronous confirm the theoretically expected assumption that asynchronous approaches are more suitable for operating in distributed memory architectures than those of a synchronous nature.
...
...